Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
PKU-Alignment
/
beaver-7b-v1.0-reward
like
16
Follow
PKU-Alignment
62
Reinforcement Learning
Safetensors
PKU-Alignment/PKU-SafeRLHF
English
safe-rlhf
llama
reinforcement-learning-from-human-feedback
beaver
safety
ai-safety
deepspeed
rlhf
alpaca
arxiv:
2302.13971
arxiv:
2307.04657
arxiv:
2310.12773
Model card
Files
Files and versions
Community
2
Train
refs/pr/2
beaver-7b-v1.0-reward
2 contributors
History:
9 commits
SFconvertbot
Adding `safetensors` variant of this model
562b3c7
verified
10 months ago
.gitattributes
1.52 kB
initial commit
over 1 year ago
README.md
2.61 kB
Update README.md
over 1 year ago
added_tokens.json
21 Bytes
hello beaver reward model
over 1 year ago
config.json
539 Bytes
Update architecture name in config.json
about 1 year ago
pytorch_model-00001-of-00004.bin
pickle
Detected Pickle imports (4)
"torch._utils._rebuild_tensor_v2"
,
"torch.BFloat16Storage"
,
"collections.OrderedDict"
,
"torch.FloatStorage"
What is a pickle import?
3.97 GB
LFS
hello beaver reward model
over 1 year ago
pytorch_model-00001-of-00004.safetensors
3.97 GB
LFS
Adding `safetensors` variant of this model
10 months ago
pytorch_model-00002-of-00004.bin
pickle
Detected Pickle imports (4)
"torch._utils._rebuild_tensor_v2"
,
"torch.BFloat16Storage"
,
"collections.OrderedDict"
,
"torch.FloatStorage"
What is a pickle import?
3.98 GB
LFS
hello beaver reward model
over 1 year ago
pytorch_model-00002-of-00004.safetensors
3.98 GB
LFS
Adding `safetensors` variant of this model
10 months ago
pytorch_model-00003-of-00004.bin
pickle
Detected Pickle imports (4)
"collections.OrderedDict"
,
"torch.FloatStorage"
,
"torch._utils._rebuild_tensor_v2"
,
"torch.BFloat16Storage"
What is a pickle import?
3.96 GB
LFS
hello beaver reward model
over 1 year ago
pytorch_model-00003-of-00004.safetensors
3.96 GB
LFS
Adding `safetensors` variant of this model
10 months ago
pytorch_model-00004-of-00004.bin
pickle
Detected Pickle imports (4)
"torch._utils._rebuild_tensor_v2"
,
"torch.BFloat16Storage"
,
"collections.OrderedDict"
,
"torch.FloatStorage"
What is a pickle import?
1.3 GB
LFS
hello beaver reward model
over 1 year ago
pytorch_model-00004-of-00004.safetensors
1.3 GB
LFS
Adding `safetensors` variant of this model
10 months ago
pytorch_model.bin.index.json
26.8 kB
hello beaver reward model
over 1 year ago
special_tokens_map.json
435 Bytes
hello beaver reward model
over 1 year ago
tokenizer.model
500 kB
LFS
hello beaver reward model
over 1 year ago
tokenizer_config.json
726 Bytes
hello beaver reward model
over 1 year ago
